</term>
of the
<term>
corpus
</term>
, in particular
#28138A major concern in corpus based approaches is that the applicability of the acquired knowledge may be limited by somefeature of the corpus, in particular, the notion of text 'domain'.
other,23-4-A97-1015,ak
</term>
or the same
<term>
class
</term>
(
<term>
fiction
</term>
or
<term>
nonfiction
</term>
) . We will
#28236The parsing results show that the best accuracy is obtained using the grammar acquired from the same domain or the same class (fiction or nonfiction).
other,17-4-A97-1015,ak
grammar
</term>
acquired from the same
<term>
domain
</term>
or the same
<term>
class
</term>
(
<term>
#28230The parsing results show that the best accuracy is obtained using the grammar acquired from the samedomain or the same class (fiction or nonfiction).
tech,1-4-A97-1015,ak
<term>
syntactic structure
</term>
. The
<term>
parsing results
</term>
show that the best
<term>
accuracy
</term>
#28214Theparsing results show that the best accuracy is obtained using the grammar acquired from the same domain or the same class (fiction or nonfiction).
tech,36-2-A97-1015,ak
specific structures
</term>
; and 3 )
<term>
Parsing experiment
</term>
using some
<term>
domain dependent
#28190In order to examine the domain dependence of parsing, in this paper, we report 1) Comparison of structure distributions across domains; 2) Examples of domain specific structures; and 3)Parsing experiment using some domain dependent grammars.